Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 2905 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.4911. Min Range: -0.4911

Max Act: 0.4911. Min Act: -0.0001

Data Index: 343179 (C4 (Web Text))

Max Activating Token Index: 653

Text #1

Max Range: 0.4911. Min Range: -0.4911

Max Act: 0.4601. Min Act: -0.0001

Data Index: 592149 (C4 (Web Text))

Max Activating Token Index: 428

Text #2

Max Range: 0.4911. Min Range: -0.4911

Max Act: 0.4149. Min Act: -0.0001

Data Index: 1017840 (C4 (Web Text))

Max Activating Token Index: 610

Text #3

Max Range: 0.4911. Min Range: -0.4911

Max Act: 0.4537. Min Act: -0.0001

Data Index: 44365 (C4 (Web Text))

Max Activating Token Index: 670

Text #4

Max Range: 0.4911. Min Range: -0.4911

Max Act: 0.4279. Min Act: -0.0001

Data Index: 181836 (C4 (Web Text))

Max Activating Token Index: 592

Text #5

Max Range: 0.4911. Min Range: -0.4911

Max Act: 0.4075. Min Act: -0.0001

Data Index: 991261 (C4 (Web Text))

Max Activating Token Index: 790

Text #6

Max Range: 0.4911. Min Range: -0.4911

Max Act: 0.4182. Min Act: -0.0001

Data Index: 504059 (C4 (Web Text))

Max Activating Token Index: 855

Text #7

Max Range: 0.4911. Min Range: -0.4911

Max Act: 0.4033. Min Act: -0.0001

Data Index: 341114 (C4 (Web Text))

Max Activating Token Index: 903

Text #8

Max Range: 0.4911. Min Range: -0.4911

Max Act: 0.4080. Min Act: -0.0001

Data Index: 1065005 (C4 (Web Text))

Max Activating Token Index: 761

Text #9

Max Range: 0.4911. Min Range: -0.4911

Max Act: 0.4467. Min Act: -0.0001

Data Index: 531358 (C4 (Web Text))

Max Activating Token Index: 688

Text #10

Max Range: 0.4911. Min Range: -0.4911

Max Act: 0.4141. Min Act: -0.0001

Data Index: 67251 (C4 (Web Text))

Max Activating Token Index: 589

Text #11

Max Range: 0.4911. Min Range: -0.4911

Max Act: 0.3879. Min Act: -0.0001

Data Index: 821563 (C4 (Web Text))

Max Activating Token Index: 745

Text #12

Max Range: 0.4911. Min Range: -0.4911

Max Act: 0.4111. Min Act: -0.0001

Data Index: 28172 (C4 (Web Text))

Max Activating Token Index: 788

Text #13

Max Range: 0.4911. Min Range: -0.4911

Max Act: 0.4095. Min Act: -0.0001

Data Index: 951672 (C4 (Web Text))

Max Activating Token Index: 603

Text #14

Max Range: 0.4911. Min Range: -0.4911

Max Act: 0.3696. Min Act: -0.0001

Data Index: 1231722 (C4 (Web Text))

Max Activating Token Index: 990

Text #15

Max Range: 0.4911. Min Range: -0.4911

Max Act: 0.4031. Min Act: -0.0001

Data Index: 506971 (C4 (Web Text))

Max Activating Token Index: 503

Text #16

Max Range: 0.4911. Min Range: -0.4911

Max Act: 0.4010. Min Act: -0.0001

Data Index: 938122 (C4 (Web Text))

Max Activating Token Index: 771

Text #17

Max Range: 0.4911. Min Range: -0.4911

Max Act: 0.3808. Min Act: -0.0001

Data Index: 1034759 (C4 (Web Text))

Max Activating Token Index: 278

Text #18

Max Range: 0.4911. Min Range: -0.4911

Max Act: 0.3785. Min Act: -0.0001

Data Index: 989252 (C4 (Web Text))

Max Activating Token Index: 934

Text #19

Max Range: 0.4911. Min Range: -0.4911

Max Act: 0.3868. Min Act: -0.0001

Data Index: 1168236 (C4 (Web Text))

Max Activating Token Index: 258